INDEX

Explanations

technical terms and variables associated with programming and configuration settings

oai_token-act-pair · gpt-4o-mini Triggered by @bot

starting with a capital letter

np_acts-logits-general · gemini-2.0-flash

Programming configurations and code

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

•SQL-labeled features

(not SQL, but also lights up for SQL code)

No Comments

Negative Logits

</h2>

-0.67

</strong>

-0.62

</u>

-0.58

”

-0.54

</b>

-0.54

</em>

-0.53

</h1>

-0.52

...

-0.50

…

-0.50

POSITIVE LOGITS

 مرئيه

1.21

 ſeveral

0.97

 poffe

0.95

 Theſe

0.94

 ſtre

0.93

 otomatig

0.92

 myſelf

0.92

 дописавши

0.92

RenderAtEndOf

0.92

Efq

0.91

Activations Density 0.609%

technical terms and variables associated with programming and configuration settings

starting with a capital letter

Programming configurations and code

No Comments

No Known Activations